无标题文档
论文摘要内容

题名:

 短期负荷预测方法改进及应用研究

作者:

 冯煜坤

语种:

 chi

学科:

 电力系统及其自动化

学位:

 工程硕士

学校:

 南京工程学院

院系:

 电力工程学院

专业:

 电气工程

导师姓名:

 张仰飞

完成日期:

 2015-05-30

题目(外文):

 Application Research on Improved Methods of Short-time Load Forecasting

关键字(中文):

 短期负荷预测 BP 神经网络 弹性梯度下降法 MISO 多项式神经网络

关键字(外文):

 short-term load forecasting back propagation neural network polynomial feed forward artificial neural network

文摘:

 

负荷预测是电力系统调度、 运行过程中必不可少的一个重要环节。 负荷预测值的准 确度对于电力系统进行停机计划、 安全评估具有重要影响, 并且对电力系统运行成本产 生直接影响。 由于电力生产的实时性与瞬发性, 短期负荷预测一直是负荷预测领域最重 要的和最热门的研究方向。 虽然配网自动化平台已经广泛应用于地方供电公司 , 但负荷预测的功能却并没有广 泛配置, 而有的平台虽然集成了高级应用, 然而负荷预测模块却仍采用传统方法, 由于 负荷与影响因素之间的非线性关系, 传统方法并不能满足负荷预测的精度要求。 而且随 着智能电网的建设, 相应的配网自动化平台也亟需更新, 开发新的负荷预测模块也很有 必要。 作为负荷预测模块中核心的算法部分, 人工智能方法由于其自适应、 自学习 性, 得到了 世界主流电力自动化企业的重视, 而其中又以人工神经网络最为突出。 本文简述了电力系统负荷预测的发展现状、 各类预测方法的特点, 阐述了 论文选题 的工程背景, 分析了 电力系统短期负荷预测中电力负荷的特点和变化规律, 分析了 影响 负荷预测的其他相关因素。 利用 五种改进 BP 神经网络以国电南自提供的西北某地区 2013 年负荷数据作为研究样本进行了负荷预测的研究与对比分析, 对原始数据的分布情 况作了分析, 选取了合适的区段作为预测训练和对照样本, 对比五种不同的改进误差算 法在多输入多输出模型策略下的误差及准确率。 针对其单点预测精度不够的问题, 进一 步改进了预测策略, 重新构建了多输入单输出的 MISO 多项式神经网络模型, 提出了多 项式伪逆权值优化法, 预测结果表明, 改进后的方法预测精度有显著提高。 通过 VB 与 MATLAB 混合编程开发出了负荷预测软件, 为项目 的工程化应用做出了 有益尝试。

文摘(外文):

 

Short-term load forecast is an essential part of electric power system planning and operation. Forecasted values of system load affect the decisions made for unit commitment and security assessment, which have a direct impact on operational costs and system security. Short-term load forecasting has been the most important and the most popular research field of load forecasting for instantaneity of electric power production. Although the distribution automation platform has been widely used in local utility, the function of load forecasting has not widely deployed. Although some platform integrates advanced application and load forecast module with traditional method, but traditional methods cannot meet the needs of the load forecasting precision. As the construction of the smart grid, the corresponding distribution network automation platform as well as load forecasting module also needs to be updated. As the core of the algorithm components of load forecast module, artificial intelligence methods wildly used in the world-leading power automation company. The northwest region 2013 load data provided by the SAC selected as the research samples. The distribution of original data were analyzed by MATLAB2012 neural network toolbox, appropriate section selected as the prediction and contrast sample, and two different kinds of load forecasting model were constructed. Five different improved error back propagation neural network under different model accuracy were compared. Putting forward a MISO forecasting method to solve this problem,. The results of this method indicate that forecasting precision improved significantly. Making a significant trial for engineering by developing a load forecasting software using VB and Matlab.

参考文献:

[1] Tao, Hong. Short Term Electric Load Forecasting[D]. Raleigh, North Carolina State University, 2010. [2] A. D. Papalexopoulos and T. C. Hesterberg,"A regression-based approach to short-term system load forecasting," IEEE Transactions on Power Systems,vol. 5, pp. 1535-1547, 1990. [3] M. T. Hagan and S. M. Behr, "The Time Series Approach to Short Term Load Forecasting," IEEE Transactions on Power Systems, vol. 2, pp. 785-791,1987. [4] H. S. Hippert, C. E. Pedreira, and R. C. Souza, "Neural networks for short-term load forecasting: a review and evaluation," IEEE Transactions on Power Systems, vol. 16, pp. 44-55, 2001. [5] A. Khotanzad, R. Afkhami-Rohani, L. Tsun-Liang, A. Abaye, M. Davis, and D. J. Maratukulam, "ANNSTLF-a neural-network-based electric load. [6] A. Khotanzad, R. Afkhami-Rohani, and D. Maratukulam, "ANNSTLF-Artificial Neural Network Short-Term Load Forecaster generation three,"IEEE Transactions on Power Systems, vol. 13, pp. 1413-1422, 1998. [7] A. Khotanzad, Z. Enwang, and H. Elragal, "A neuro-fuzzy approach to short-term load forecasting in a price-sensitive environment," IEEE Transactions onPower Systems, vol. 17, pp. 1273-1282, 2002. [8] A. Khotanzad, M. H. Davis, A. Abaye, and D. J. Maratukulam, "An artificial neural network hourly temperature forecaster with applications in loadforecasting," IEEE Transactions on Power Systems, vol. 11, pp. 870-876,1996. [9] K. Methaprayoon, W.-J. Lee, S. Rasmiddatta, J. R. Liao, and R. J. Ross,"Multistage Artificial Neural Network Short-Term Load Forecasting Engine With Front-End Weather Forecast," IEEE Transactions on Industry Applications, vol. 43, pp. 1410-1416, 2007. [10] J. S. Armstrong, "Strategic Planning And Forecasting Fundamentals," General Economics and Teaching 0502066, EconWPA, 2005. [11] G. E. Huck, A. A. Mahmoud, R. B. Comerford, J. Adams, and E. Dawson,"Load Forecast Bibliography Phase I," IEEE Transactions on Power Apparatus and Systems, vol. PAS-99, pp. 53-58, 1980. [12] A. A. Mahmoud, T. H. Ortmeyer, and R. E. Reardon, "Load Forecasting Bibliography Phase II," IEEE Transactions on Power Apparatus and Systems,vol. PAS-100, pp. 3217-3220, 1981. [13] M. A. Abu-El-Magd and N. K. Sinha, "Short-Term Load Demand Modeling and Forecasting: A Review," IEEE Transactions on Systems, Man and Cybernetics, vol. 12, pp. 370-382, 1982. [14] G. Gross and F. D. Galiana, "Short-term load forecasting," Proceedings of the IEEE, vol. 75, pp. 1558-1573, 1987. [15] H. S. Hippert, C. E. Pedreira, and R. C. Souza, "Neural networks for short-term load forecasting: a review and evaluation," IEEE Transactions on Power Systems, vol. 16, pp. 44-55, 2001. [16] K. Metaxiotis, A. Kagiannas, D. Askounis, and J. Psarras, "Artificial intelligence in short term electric load forecasting: a state-of-the-art survey for the researcher," Energy Conversion and Management, vol. 44, pp. 1525-1534,2003. [17] I. Moghram and S. Rahman, "Analysis and evaluation of five short-term load forecasting techniques," IEEE Transactions on Power Systems, vol. 4, pp.1484-1491, 1989. [18] H. S. Hippert and C. E. Pedreira, "Estimating temperature profiles for short-term load forecasting: neural networks compared to linear models," IEEE Proceedings - Generation, Transmission and Distribution, vol. 151, pp. 543-547, 2004. [19] K. Liu, S. Subbarayan, R. R. Shoults, M. T. Manry, C. Kwan, F. I. Lewis, and J. Naccarino, "Comparison of very short-term load forecasting techniques," IEEE Transactions on Power Systems, vol. 11, pp. 877-882, 1996. [20] J. W. Taylor and P. E. McSharry, "Short-Term Load Forecasting Methods: An Evaluation Based on European Data," IEEE Transactions on Power Systems vol. 22, pp. 2213-2219, 2007. [21] K.-B. Song, S.-K. Ha, J.-W. Park, D.-J. Kweon, and K.-H. Kim, "Hybrid load forecasting method with analysis of temperature sensitivities," IEEE Transactions on Power Systems, vol. 21, pp. 869-876, 2006. [22]尹新. 群智能算法与电力负荷预测研究[D].湖南大学,2011. [23]贺辉. 电力负荷预测和负荷管理[M]. 北京: 中国电力出版社, 2013: 51-52. [24]张雨浓, 杨逸文, 李巍. 神经网络权值直接确定法[M]. 广州: 中山大学出 版社, 2010: 48-49. [25]丛爽. 面向 MATLAB 工具箱的神经网络理论与应用[M]. 合肥:中国科学技术 大学出版社, 2009. [26]刘晓娟. 基于智能方法的电力系统负荷预测模型及其应用研究[D].东华大学 ,2014. [27]蔡剑彪. 基于云计算的智能电网负荷预测平台研究[D].湖南大学,2013. [28]罗滇生,李伟伟,何洪英.基于局部形相似的超短期负荷预测方法[J].电力系统 及其自动化学报. 2008.20(1):75-79. [29]史会峰. 基于贝叶斯理论 MCMC 优化参数的负荷预测模型[D].华北电力大学 ,2013. [30]李云飞,黄彦全,蒋功连.基于支持向量机的短期负荷预测的方法改进[J].西华 大学学报 2007, 26(2). [31]焦建林,芦晶晶.基于改进时间序列法的配电网短期负荷预测模型[J].电工技术 杂志,2002,5:25-28. [32]牛丽仙,苑津莎,张英慧,基于粗糙集和支持向量机的电力系统短期负荷预测 [J].电力科学与工程. 2010,26(2):32-35. [33]张庆尘,程浩忠,刘青山等.基于粗糙集属性约简算法和支持向量机的短期负荷 预测[J].电网技术. 2006,30(8):56-59. [34]杨龙. 基于神经网络的短期负荷预测的研究与实现[D].湖南中南大学, 2009. [35]王贞珍.基于神经网络的沈阳地区短期负荷预测[D].上海:上海交通大学,2009. [36]赵璐. 基于人工神经网络的电力系统负荷预测[J].硅谷电子科学, 2008(8):22. [37]陈耀武, 汪乐宁, 龙洪玉.基于组合式神经网络的短期电力负荷预测模型 [J]. 中国电机工程学报. 2001.2l(4): 79-82. [38] S.M.R. Kazemi,Mir Meisam Seied Hoseini,S. Abbasian‐ Naghneh,Seyed Habib A. Rahmati. An evolutionary‐ based adaptive neuro‐ fuzzy inference system for intelligent short‐ term load forecasting[J]. Intl. Trans. in Op. Res.,2014,212. [39] Shahid M. Awan,Muhammad Aslam,Zubair A. Khan,Hassan Saeed. An efficient model based on artificial bee colony optimization algorithm with NeuralNetworks for electric load forecasting[J]. Neural Computing and Applications,2014,257-8. [40] Hossein Hassani,Majid Abdollahzadeh,Hossein Iranmanesh,Arash Miranian. A self-similar local neuro-fuzzy model for short-term demand forecasting[J].Journal of Systems Science and Complexity,2014,271. [41]莫维仁, 张伯明, 孙宏斌, 胡子珩. 短期负荷预测中选择相似日的探讨[J]. 清华大学学报(自然科学版),2004,01: 106-109. [42]廖旎焕,胡智宏,马莹莹,卢王允. 电力系统短期负荷预测方法综述[J]. 电力系统保护与控制,2011,01:147-152 [43]李青,李军,马昊. 基于互补型集成经验模态分解-模糊熵和回声状态网络的短期电力负荷预测[J]. 计算机应用,2014,12. [44]关学忠,佟宇,高哲,皇甫旭,聂品磊,白云龙. 基于分形理论的短期电力负荷预测[J]. 计算机与数字工程,2014,11.

﹀展开
开放日期:

 2018-07-01

无标题文档